LAHNet：用于点云配准的局部注意哈希网络
LAHNet: Local Attentive Hashing Network for Point Cloud Registration
AI总结：
LAHNet通过引入局部注意机制和高效窗口化策略，提升点云配准的特征区分性与鲁棒性。
摘要：
现有的基于学习的点云描述符大多专注于感知点云的局部信息以生成独特的特征。然而，一个合理且更广的感受野对于增强特征的区分性至关重要。在本文中，我们提出了一种用于点云配准的局部注意哈希网络（LAHNet），该网络将具有局部性归纳偏差的卷积样操作的局部注意机制引入到点云描述符中。具体来说，设计了一个分组变换器以捕捉点之间合理长程上下文。该方法采用线性邻域搜索策略，局部敏感哈希，使点云能够均匀地划分为非重叠窗口。同时，采用高效的跨窗口策略进一步扩展合理特征感受野。此外，基于这一有效的窗口化策略，我们提出了一种交互变换器以增强点云对中重叠区域的特征交互。该方法计算一个重叠矩阵，通过将每个窗口表示为全局信号来匹配点云对之间的重叠区域。大量实验结果表明，LAHNet能够学习到稳健且独特的特征，在现实世界中的室内和户外基准上实现了显著的配准结果。
英文摘要：
Most existing learning-based point cloud descriptors for point cloud registration focus on perceiving local information of point clouds to generate distinctive features. However, a reasonable and broader receptive field is essential for enhancing feature distinctiveness. In this paper, we propose a Local Attentive Hashing Network for point cloud registration, called LAHNet, which introduces a local attention mechanism with the inductive bias of locality of convolution-like operators into point cloud descriptors. Specifically, a Group Transformer is designed to capture reasonable long-range context between points. This employs a linear neighborhood search strategy, Locality-Sensitive Hashing, enabling uniformly partitioning point clouds into non-overlapping windows. Meanwhile, an efficient cross-window strategy is adopted to further expand the reasonable feature receptive field. Furthermore, building on this effective windowing strategy, we propose an Interaction Transformer to enhance the feature interactions of the overlap regions within point cloud pairs. This computes an overlap matrix to match overlap regions between point cloud pairs by representing each window as a global signal. Extensive results demonstrate that LAHNet can learn robust and distinctive features, achieving significant registration results on real-world indoor and outdoor benchmarks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
